© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 119025
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional struggles and personal challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ·ãĥ¥
    -0.07
    Assertions
    -0.07
    lette
    -0.07
    ditor
    -0.07
    shint
    -0.07
    deme
    -0.07
    éŁ¿
    -0.07
     Contrast
    -0.07
    RectTransform
    -0.07
    üçük
    -0.06
    POSITIVE LOGITS
     otherwise
    0.06
    èĿ
    0.06
     us
    0.06
    zs
    0.06
     grip
    0.05
    åĿĤ
    0.05
    Æ°á»Ľ
    0.05
     them
    0.05
    ms
    0.05
     everyone
    0.05
    Activations Density 0.027%

    No Known Activations